Topic: Condition Monitoring, Diagnosis and Predictive Maintenance of Complex Engineering Equipment

With the continuous progress of modern science and technology, complex engineering equipment (e.g., wind turbines, aero-engine, crane machinery, railway traffic equipment) is rapidly evolving toward increased automation, intelligence, and efficiency. Condition monitoring, diagnosis and predictive maintenance of engineering equipment can be summarized as a comprehensive process. It involves using scientific methods for real-time monitoring of equipment operation status, employing advanced signal processing and fault diagnosis technology to accurately identify abnormal parts, deterioration levels, and development trends, and developing targeted and reasonable preventive and maintenance management strategies. Additionally, it is not only a key measure to avoid downtime accidents, reduce production risks, and improve equipment reliability, but also an effective guarantee to help enterprises operate efficiently, optimize industrial production efficiency, and reduce economic losses. It is a key development area that has attracted special attention from numerous domestic and foreign research institutions, including universities, enterprises, and research institutes. Against this backdrop, this Special Issue has been organized to present the latest advancements in condition monitoring, diagnosis, and predictive maintenance of complex engineering equipment in various fields such as machinery, electrical, civil engineering, and chemical engineering.

This Special Issue aims to collect the latest research findings in the condition monitoring, diagnosis, and predictive maintenance of engineering equipment, while promoting the development of relevant theoretical methods and practical engineering applications in this field. Main topics include (but are not limited to):
1. System dynamics modeling;
2. Wired/wireless sensors and network communication technology;
3. Analysis and processing methods for non-stationary signals;
4. Physical model-based/knowledge-based/data-driven fault diagnosis and predictive maintenance techniques;
5. Software and hardware systems and automatic control technologies for condition monitoring and fault diagnosis of complex engineering equipment.

Dynamics modeling, digital twin, sensor technology, network communication technology, signal processing, feature extraction, fault diagnosis, pattern recognition, life prediction, control strategy, edge computing, federated learning, deep learning, transfer learning, reinforcement learning; meta-learning; graph learning

30 Apr 2025